Optimizing marker planning in apparel production using evolutionary strategies and neural networks

Marker planning in apparel production is a kind of packing problem in the research field of engineering. The irregular shapes of pattern pieces of a garment make the marker planning problem more complex. Few approaches have been developed to solve these problems, although effectiveness of packing determines industrial resource utilization. This study constructs a packing approach that integrates a grid approximation-based representation, a learning vector quantization neural network, a heuristic placement strategy and an integer representation-based(. μ+. λ) - evolutionary strategy to obtain efficient placement of irregular objects. Real data are used to demonstrate the performance of the proposed methodology. The results are compared with those obtained by a genetic algorithm-based packing approach and those generated from industrial practice, demonstrating the effectiveness of the proposed approach.